Triple
T22068315
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FBI Operation Desert Glow |
E545337
|
entity |
| Predicate | investigatedFacilityType |
P146489
|
FINISHED |
| Object | nuclear weapons plant |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: nuclear weapons plant | Statement: [FBI Operation Desert Glow, investigatedFacilityType, nuclear weapons plant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: investigatedFacilityType Context triple: [FBI Operation Desert Glow, investigatedFacilityType, nuclear weapons plant]
-
A.
fccFacilityType
Indicates the specific type or classification of a facility as defined by the FCC (Federal Communications Commission).
-
B.
designedFacilityType
Indicates the type or category of facility that something (such as a plan, system, or component) is specifically designed for.
-
C.
usedAtFacilityType
Indicates that something is utilized or applied within a facility of a specified type.
-
D.
hasFacilityType
Indicates that an entity possesses or is associated with a specific type or category of facility.
-
E.
primaryFacilityType
Indicates the main or predominant type or category of facility associated with an entity.
- F. None of above. chosen
Provenance (4 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e11e344dfc81909b1d88a7221329c7 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12885fe04819092cdde142f91e147 |
completed | April 28, 2026, 9:37 p.m. |
| PD | Predicate disambiguation | batch_69e6f64a6a70819089d1a6c3a2384861 |
completed | April 21, 2026, 4 a.m. |
| PDg | Predicate description generation | batch_69e6fad4a540819096cdd5ea08527220 |
completed | April 21, 2026, 4:19 a.m. |
Created at: April 16, 2026, 8:27 p.m.